A discriminative model-constrained EM approach to 3D MRI brain tissue classification and intensity non-uniformity correction
Physics in Medicine and Biology
We describe a fully automated method for tissue classification, which is the segmentation into cerebral gray matter (GM), cerebral white matter (WM), and cerebral spinal fluid (CSF), and intensity non-uniformity (INU) correction in brain magnetic resonance imaging (MRI) volumes. It combines supervised MRI modalityspecific discriminative modeling and unsupervised statistical expectation maximization (EM) segmentation into an integrated Bayesian framework. While both the parametric observation
... els as well as the non-parametrically modeled INUs are estimated via EM during segmentation itself, an Markov random field (MRF) prior model regularizes segmentation and parameter estimation. Firstly, the regularization takes into account knowledge about spatial and appearance related homogeneity of segments in terms of pairwise clique potentials of adjacent voxels. Secondly and more importantly, patientspecific knowledge about the global spatial distribution of brain tissue is incorporated into the segmentation process via unary clique potentials. They are based on a strong discriminative model provided by a probabilistic boosting-tree (PBT) for classifying image voxels. It relies on surrounding context and alignment-based features derived from a probabilistic anatomical atlas. The context considered is encoded by 3-D Haarlike features of reduced INU sensitivity. Alignment is carried out fully automatically by means of an affine registration algorithm minimizing cross-correlation. Both types of features do not immediately use the observed intensities provided by the MRI modality but instead rely on specifically transformed features, which are less sensitive to MRI artifacts. Detailed quantitative evaluations on standard phantom scans and standard real world data show the accuracy and robustness of the proposed method. They also demonstrate relative superiority in comparison to other state-of-the-art approaches to this kind of computational task: our method achieves average Dice coefficients of 0.93 ± 0.03 (WM) and 0.90 ± 0.05 (GM) on simulated mono-spectral and 0.94 ± 0.02 (WM) and 0.92 ± 0.04 (GM) on simulated multi-spectral data from the BrainWeb repository. The scores are 0.81±0.09 (WM) and 0.82±0.06 (GM) and 0.87±0.05 (WM) and 0.83±0.12 (GM) for the two collections of real-world data sets-consisting of 20 and 18 volumes, respectively-provided by the Internet Brain Segmentation Repository. 3-D MRI Brain Tissue Classification and Intensity Non-Uniformity Correction 6 Keywords: brain tissue classification, segmentation, intensity non-uniformity correction, magnet resonance imaging, Markov random fields, expectation-maximization, probabilistic boosting-tree, discriminative modeling Submitted to: Phys. Med. Biol. † Although not detailed in the original publication a multi-spectral implementation of Zhang et al. 's method (Zhang et al., 2001) already exists and can be downloaded from www.fmrib.ox.ac.uk/fsl.